← The AI Systems Map
L2 · ChipsFramework / tooling

NVIDIA TensorRT-LLM / Dynamo

NVIDIA's optimized inference compiler and disaggregated serving

TensorRT-LLM plus the newer Dynamo distributed-inference framework are NVIDIA's answer to open serving stacks, delivering kernel-fused, FP4/FP8-optimized inference and KV-aware routing across Blackwell/Rubin racks. Together with Triton Inference Server they lock inference performance to CUDA and are a key part of the software moat that keeps GB200/GB300 utilization high.

Precision

FP8/FP4 (Blackwell)

Pairs with

Triton, NIM microservices

How it fits the stack

NVIDIA TensorRT-LLM / Dynamo with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.

depends onusesdepends ondesignsNVIDIA TensorRT-LLM /DynamoChipsCUDA / software moatchokepointKV-cache & inferencememory tieringNvidia Data-Center GPU(Blackwell/Rubin)chokepointNvidia
NVIDIA TensorRT-LLM / DynamoDepends on ↑Related

NVIDIA TensorRT-LLM / Dynamo in the AI stack. NVIDIA TensorRT-LLM / Dynamo with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.

Graph data (text) — 5 entities, 4 relationships
  • NVIDIA TensorRT-LLM / Dynamodepends onCUDA / software moat
  • NVIDIA TensorRT-LLM / DynamousesKV-cache & inference memory tiering
  • NVIDIA TensorRT-LLM / Dynamodepends onNvidia Data-Center GPU (Blackwell/Rubin)
  • NVIDIA TensorRT-LLM / DynamodesignsNvidia

Context — capital, rivals, policy · · 1